LLM Prompt Specialist

The LLM Prompt Specialist will shape the future of AI-powered applications by designing advanced prompt strategies, agent workflows, and scalable LLM solutions. This role combines software engineering, artificial intelligence, and product innovation.

Responsibilities

• Define and lead the development of prompt engineering strategies, AI workflows, and technical patterns for scalable LLM-powered applications.
• Combine hands-on engineering expertise with architectural thinking to improve AI capabilities across teams.
• Design and establish prompt engineering strategies, reusable patterns, and best practices for LLM-based applications.
• Build and optimize agent workflows, prompt architectures, and AI-powered application frameworks.
• Develop evaluation pipelines and methodologies to measure the quality, reliability, and performance of non-deterministic AI systems.
• Create scalable solutions using modern LLM APIs, retrieval-augmented generation (RAG), embeddings, and vector databases.
• Develop and deploy production-ready AI applications while ensuring performance, reliability, and responsible AI practices.
• Partner with engineering teams to integrate LLM technologies into enterprise software solutions.
• Provide technical guidance and mentorship to engineers working on AI-related initiatives.
• Influence architectural decisions and define standards for AI application development.
• Evaluate emerging LLM technologies and recommend appropriate approaches based on business and technical needs.
• Ensure AI solutions follow responsible AI principles, including safety, compliance, and policy considerations.

Requirements

• An experienced software engineer and AI practitioner with a strong background in building and scaling LLM-powered applications.
• Significant experience developing LLM-based applications and delivering AI-powered products or solutions into production environments.
• Strong knowledge of modern LLM APIs, agent frameworks, and AI application architectures.
• Hands-on experience with retrieval-augmented generation, embeddings, and vector database technologies.
• Experience designing evaluation frameworks for AI systems with variable outputs.
• Strong Python development skills and familiarity with modern application frameworks.
• Understanding of responsible AI concepts, including safety, governance, and policy considerations.
• Excellent written and verbal communication skills with the ability to explain complex technical concepts.
• Experience mentoring engineers and influencing technical strategy.
• Familiarity with multi-agent architectures, tool-use systems, fine-tuning workflows, and enterprise AI integrations is a plus.
• Experience contributing through technical writing, public speaking, or open-source projects is a plus.

Benefits

• A competitive annual salary range of $100,000-$150,000, based on experience and qualifications.
• A fully remote position available across the United States.
• A full-time direct employment opportunity.
• The opportunity to work on innovative AI initiatives and enterprise-scale solutions.
• Career growth opportunities within a technology-focused environment.